GCN-WP -- Semi-Supervised Graph Convolutional Networks for Win Prediction in Esports

TL;DR

This paper introduces GCN-WP, a semi-supervised graph convolutional network model that predicts esports match outcomes by learning league structures over a season, achieving state-of-the-art accuracy and generalizability.

Contribution

The paper presents a novel semi-supervised GCN model for esports win prediction that captures league dynamics and outperforms existing machine learning and skill rating methods.

Findings

Achieves state-of-the-art prediction accuracy for LoL.

Effectively models league structure over a season.

Generalizable framework for other multiplayer games.

Abstract

Win prediction is crucial to understanding skill modeling, teamwork and matchmaking in esports. In this paper we propose GCN-WP, a semi-supervised win prediction model for esports based on graph convolutional networks. This model learns the structure of an esports league over the course of a season (1 year) and makes predictions on another similar league. This model integrates over 30 features about the match and players and employs graph convolution to classify games based on their neighborhood. Our model achieves state-of-the-art prediction accuracy when compared to machine learning or skill rating models for LoL. The framework is generalizable so it can easily be extended to other multiplayer online games.